CCS2011: Enemy of the Good

Title

How to Evaluate Intrusion Detection Systems

Introduction

• Evaluating non-adaptive IDSs (signature, specification) is like evaluating a programming language
  • quality of individual solutions does not indicate quality of framework
  • quality over all solutions might say something, but that is very hard to measure

• Adaptive IDSs has been seen as a machine learning problem, but it really isn't.
• Multiple papers criticizing specific ML approaches to IDS [CITES]
• Problem is general

• Why?
  • [1]

Sections:

• Problem

What Goes Wrong

• Poor results
  • datasets do not represent real-world usage or scenarios accurately
  • insufficient or misleading tests of false positive rates
  • Even when rates are accurate, they are misinterpreted: high FP rates are not considered to be high (wrong time scale, lack of attention to scalability)
  • misleading integration of attacks into legitimate behavior
• Administrative overhead
  • rules that can only be created by experts, but system requires end users to create custom rules
  • experts required to interpret output
  • insufficient context for even experts to interpret output
  • assumption of existence of security personnel that won't even exist in many important contexts
• Computational overhead
  • can system keep up with normal workloads?
  • can system keep up with attacker-generated workloads?
• Anomalies versus attacks
  • why is one a good proxy for the other?
  • why is chosen feature(s) particularly good at detecting attacks?
• Out of the box algorithms applied w/o understanding security problem
• Attacker evasion: how can attacker manipulate system? Can system lead to environment that is easier to attack?